A frequent problem of traffic flow characteristics acquisition is data loss, which leads to uneven time series analysis. An effective approach to uneven data analysis is the spectral analysis, which requires obtaining process with a constant sampling interval, for example, by restoring missing data, which leads to the appearance of dating error. Thus, the main purpose of this study is to develop a method and software for wavelet analysis of traffic flow characteristics without restoring the missing data.
To analyze and interpret non-stationary uneven time series obtained from traffic monitoring systems, we propose the wavelet transformation method with adjustment of the sampling intervals, which results in a time-frequency domain with a constant sampling interval. Wavelet analysis is applied to the macroscopic traffic flow characteristics.
We developed the software for traffic flow wavelet analysis on the "ITSGIS" intelligent transport geo-information framework using the attribute-oriented approach.
Wavelet analysis of traffic flows characteristics using Morlet wavelets was accomplished for data analysis of the city of Aarhus, Denmark. Wavelet spectra and scalograms were constructed and analyzed, general dependencies in the frequency distribution of extremes, and differences in spectral power were revealed.
The developed software is being experimentally tested in solving practical problems of municipalities and road agencies in Russia.
The paper introduces a new solution for semantic analysis implementation in modern enterprise content management (ECM) systems. The system of semantic analysis is intended for the intellectual analysis of enterprise official and technical documents based on machine learning, namely the extraction of the specified attributes from them for further use. In this paper it is proposed to implement semantic search using the extracted data configurator, which is responsible for creating and managing ontologies. From the configurator of the extracted data by the name of the document type, a graph is generated containing attributes to be extracted (official terms and sections, dates, etc.), regular expressions to search for sentences that probably contain the desired attribute, Yargy and regular rules for extracting attributes from the arrays of sentences. The proposed solution was successfully probated and tested on a dataset containing engineering enterprise contract agreements and protocols.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.